diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index 0a6c86df6..0413e97b0 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -7777,7 +7777,7 @@ minimaxm3-fp4-b300-trtllm-agentic-mtp:
 # the same 3 TB AgentX ceiling before the proportional-GPU rule is applied.
 # GPU-resident points receive a zero budget.
 minimaxm3-fp4-b200-vllm-agentic-mtp:
-  image: vllm/vllm-openai:nightly-1dc464d42681d22f38caf1fdc1eb632dc4421c45
+  image: vllm/vllm-openai:nightly-8a728663c1c3eeace834a95f5654fa653cc1998c
   model: nvidia/MiniMax-M3-NVFP4
   model-prefix: minimaxm3
   runner: cluster:b200-nscale
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 6b249ea15..4de994d12 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -6921,3 +6921,12 @@
     - "Pick up the latest automatic ROCm DeepSeek-V4 optimizations, including fused mHC post/pre plus RMSNorm, gfx950 C4A top-k dispatch, fused C4 compressor GEMMs, fused SWA q/kv RMSNorm plus q FP8 quantization, and medium-batch cooperative top-k tuning."
     - "Keep the existing VLLM_ROCM_USE_AITER=1, VLLM_ROCM_USE_AITER_MOE=1, and --moe-backend aiter settings, and explicitly add VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS=1 plus VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=INT4 to both STP and MTP paths. The current checkpoint's shared-expert path does not satisfy the latest vLLM fusion conditions, so that fusion flag self-disables while preserving recipe parity."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2792
+
+- config-keys:
+    - minimaxm3-fp4-b200-vllm-agentic-mtp
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Update vLLM image from vllm/vllm-openai:nightly-1dc464d42681d22f38caf1fdc1eb632dc4421c45 (2026-08-30 nightly) to vllm/vllm-openai:nightly-d9105ea8001e0a6d77a96327d17515bb5791fb36 (2026-09-07 nightly, digest sha256:254eebf919e8b7b0d530d97fccc606c36f380ff6724d64bc190951bec1aee838, tag commit vllm-project/vllm@d9105ea8). Docker Hub last pushed the tag at 2026-09-07T06:16:01Z."
+    - "Re-pin from vllm/vllm-openai:nightly-d9105ea8001e0a6d77a96327d17515bb5791fb36 (2026-09-07 nightly) to vllm/vllm-openai:nightly-8a728663c1c3eeace834a95f5654fa653cc1998c (2026-09-04 nightly, digest sha256:f5df5cc3302b5f404848c4eca88d7bf7ed5226e151c056da22816d7734644d67; Docker Hub last pushed 2026-09-04T06:18:14Z, tag commit vllm-project/vllm@8a728663). Nightlies from 2026-09-05 onward carry vllm-project/vllm@4ee259551 (Sync FA with upstream, #54819), which moves vllm-flash-attn to 506341a1; on Blackwell the EAGLE3 draft runs FLASH_ATTN through the FA4 CuTe path and, with the fp8 KV cache, its descale tensors now fail to_cute_tensor with RuntimeError: Expected strides[leading_dim] == 1, but got 0 during CUDA-graph memory profiling, so the engine never starts (B200 run 34168437161). The 2026-09-04 nightly is the newest build still on vllm-flash-attn 06bdd47c, the same FA pin as the recipe's previous 2026-08-30 image, and the same vllm commit the MI355X MiniMax-M3 vLLM AgentX recipe already runs (nightly-8a728663). No vllm fix has landed on main as of 2026-09-08T03:00Z."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2860